The dynamic history of prokaryotic phyla: discovery, diversity and division.

Here, I review the dynamic history of prokaryotic phyla. Following leads set by Darwin, Haeckel and Woese, the concept of phylum has evolved from a group sharing common phenotypes to a set of organisms sharing a common ancestry, with modern taxonomy based on phylogenetic classifications drawn from macromolecular sequences. Phyla came as surprising latecomers to the formalities of prokaryotic nomenclature in 2021. Since then names have been validly published for 46 prokaryotic phyla, replacing some established names with neologisms, prompting criticism and debate within the scientific community. Molecular barcoding enabled phylogenetic analysis of microbial ecosystems without cultivation, leading to the identification of candidate divisions (or phyla) from diverse environments. The introduction of metagenome-assembled genomes marked a significant advance in identifying and classifying uncultured microbial phyla. The lumper-splitter dichotomy has led to disagreements, with experts cautioning against the pressure to create a profusion of new phyla and prominent databases adopting a conservative stance. The Candidatus designation has been widely used to provide provisional status to uncultured prokaryotic taxa, with phyla named under this convention now clearly surpassing those with validly published names. The Genome Taxonomy Database (GTDB) has offered a stable, standardized prokaryotic taxonomy with normalized taxonomic ranks, which has led to both lumping and splitting of pre-existing phyla. The GTDB framework introduced unwieldy alphanumeric placeholder labels, prompting recent publication of over 100 user-friendly Latinate names for unnamed prokaryotic phyla. Most candidate phyla remain 'known unknowns', with limited knowledge of their genomic diversity, ecological roles, or environments. Whether phyla still reflect significant evolutionary and ecological partitions across prokaryotic life remains an area of active debate. However, phyla remain of practical importance for microbiome analyses, particularly in clinical research. Despite potential diminishing returns in discovery of biodiversity, prokaryotic phyla offer extensive research opportunities for microbiologists for the foreseeable future.

Taxometer: Improving taxonomic classification of metagenomics contigs.

For taxonomy based classification of metagenomics assembled contigs, current methods use sequence similarity to identify their most likely taxonomy. However, in the related field of metagenomic binning, contigs are routinely clustered using information from both the contig sequences and their abundance. We introduce Taxometer, a neural network based method that improves the annotations and estimates the quality of any taxonomic classifier using contig abundance profiles and tetra-nucleotide frequencies. We apply Taxometer to five short-read CAMI2 datasets and find that it increases the average share of correct species-level contig annotations of the MMSeqs2 tool from 66.6% to 86.2%. Additionally, it reduce the share of wrong species-level annotations in the CAMI2 Rhizosphere dataset by an average of two-fold for Metabuli, Centrifuge, and Kraken2. Futhermore, we use Taxometer for benchmarking taxonomic classifiers on two complex long-read metagenomics data sets where ground truth is not known. Taxometer is available as open-source software and can enhance any taxonomic annotation of metagenomic contigs.

Efficient phylogenetic tree inference for massive taxonomic datasets: harnessing the power of a server to analyze 1 million taxa.

BACKGROUND: Phylogenies play a crucial role in biological research. Unfortunately, the search for the optimal phylogenetic tree incurs significant computational costs, and most of the existing state-of-the-art tools cannot deal with extremely large datasets in reasonable times. RESULTS: In this work, we introduce the new VeryFastTree code (version 4.0), which is able to construct a tree on 1 server using single-precision arithmetic from a massive 1 million alignment dataset in only 36 hours, which is 3 times and 3.2 times faster than its previous version and FastTree-2, respectively. This new version further boosts performance by parallelizing all tree traversal operations during the tree construction process, including subtree pruning and regrafting moves. Additionally, it introduces significant new features such as support for new and compressed file formats, enhanced compatibility across a broader range of operating systems, and the integration of disk computing functionality. The latter feature is particularly advantageous for users without access to high-end servers, as it allows them to manage very large datasets, albeit with an increase in computing time. CONCLUSIONS: Experimental results establish VeryFastTree as the fastest tool in the state-of-the-art for maximum likelihood phylogeny estimation. It is publicly available at https://github.com/citiususc/veryfasttree. In addition, VeryFastTree is included as a package in Bioconda, MacPorts, and all Debian-based Linux distributions.

How Phenograms and Cladograms Became Molecular Phylogenetic Trees.

Tree diagrams are the prevailing form of visualization in biological classification and phylogenetics. Already during the time of the so-called Systematist Wars from the mid-1960s until the 1980s most journal articles and textbooks published by systematists contained tree diagrams. Although this episode of systematics is well studied by historians and philosophers of biology, most analyses prioritize scientific theories over practices and tend to emphasize conflicting theoretical assumptions. In this article, I offer an alternative perspective by viewing the conflict through the lens of representational practices with a case study on tree diagrams that were used by numerical taxonomists (phenograms) and cladists (cladograms). I argue that the current state of molecular phylogenetics should not be interpreted as the result of a competition of views within systematics. Instead, molecular phylogenetics arose independently of systematics and elements of cladistics and phenetics were integrated into the framework of molecular phylogenetics, facilitated by the compatibility of phenetic and cladistic practices with the quantitative approach of molecular phylogenetics. My study suggests that this episode of scientific change is more complex than common narratives of battles and winners or conflicts and compromises. Today, cladograms are still used and interpreted as specific types of molecular phylogenetic trees. While phenograms and cladograms represented different forms of knowledge during the time of the Systematist Wars, today they are both used to represent evolutionary relationships. This indicates that diagrams are versatile elements of scientific practice that can change their meaning, depending on the context of use within theoretical frameworks.

Unveiling the role of taxonomic sufficiency for enhanced ecosystem monitoring.

The use of Artificial substrates (AS) as sampling devices addresses challenges in macrofaunal quantitative sampling. While effectively capturing biodiversity patterns, the time-intensitive identification process at the species level remains a substantial challenge. The Taxonomic Sufficiency approach (TS), where only taxa above species level are identified, arises as a potential solution to be tested across different environmental monitoring scenarios. In this paper, we analyzed three AS macrobenthic datasets to evaluate the odds of TS in improving the cost-effective ratio in AS monitoring studies and establish the highest resolution level to detect assemblage changes under different environmental factors. Results indicated that the family level emerged as a pragmatic compromise, balancing precision and taxonomic effort. Cost/benefit analysis supported TS efficiency, maintaining correlation stability until the family level. Results also showed that reducing resolution to family does not entail a significant Loss of Information. This study contributes to the discourse on TS applicability, highlighting its practicality in monitoring scenarios, including spatial-temporal studies, and rapid biodiversity assessments. Additionally, it highlights the "second best approach" of family-level practicality depending on the specific monitoring scenario and recognizes the importance of the species-level "best approach" before applying TS in monitoring studies.

Species delimitation 4.0: integrative taxonomy meets artificial intelligence.

Although species are central units for biological research, recent findings in genomics are raising awareness that what we call species can be ill-founded entities due to solely morphology-based, regional species descriptions. This particularly applies to groups characterized by intricate evolutionary processes such as hybridization, polyploidy, or asexuality. Here, challenges of current integrative taxonomy (genetics/genomics + morphology + ecology, etc.) become apparent: different favored species concepts, lack of universal characters/markers, missing appropriate analytical tools for intricate evolutionary processes, and highly subjective ranking and fusion of datasets. Now, integrative taxonomy combined with artificial intelligence under a unified species concept can enable automated feature learning and data integration, and thus reduce subjectivity in species delimitation. This approach will likely accelerate revising and unraveling eukaryotic biodiversity.

From the philosophy of measurement to the philosophy of classification: Generalizing the problem of coordination and historical coherentism.

The objective of this paper is twofold. First, I present a framework called historical coherentism (Chang, 2004; Tal, 2016; Van fraassen 2008) and argue that it is the best epistemological framework available to tackle the problem of coordination, an epistemic conundrum that arises with every attempt to provide empirical content to scientific theories, models or statements. Second, I argue that the problem of coordination, which has so far been theorized only in the context of measurement practices (Reichenbach, 1927; Chang, 2001; Tal, 2012; Van fraassen 2008), can be generalized beyond the philosophy of measurement. Specifically, it will be shown that the problem is embodied in classificatory practices and that, consequently, historical coherentism is well suited to analyze these practices as well as metrological ones. As a case study, I look at a contemporary debate in phylogenetics, regarding the evolutionary origin of a newly identified archaeal phylum called Methanonatronarchaeia. Exploring this debate through the lens of historical coherentism provides a detailed understanding of the dynamics of the field and a foothold for critical analyses of the standard rationale used by practitioners.

Evolutionary lability of food caching behaviour in mammals.

Food hoarding provides animals access to resources during periods of scarcity. Studies on mammalian caching indicate associations with brain size, seasonality and diet but are biased to a subset of rodents. Whether the behaviour is generalizable at other taxonomic scales and/or is influenced by other ecological factors is less understood. Population density may influence food caching due to food competition or pilferage, but this remains untested in a comparative framework. Using phylogenetic analyses, we assessed the role of morphology (body and brain size), climate, diet breadth and population density on food caching behaviour evolution at multiple taxonomic scales. We also used a long-term dataset on caching behaviour of red squirrels (Tamiasciurus fremonti) to test key factors (climate and population density) on hoarding intensity. Consistent with previous smaller scale studies, we found the mammalian ancestral state for food caching was larderhoarding, and scatterhoarding was derived. Caching strategy was strongly associated with brain size, population density and climate. Mammals with larger brains and hippocampal volumes were more likely to scatterhoard, and species living at higher population densities and in colder climates were more likely to larderhoard. Finer-scale analyses within families, sub-families and tribes indicated that the behaviour is evolutionary labile. Brain size in family Sciuridae and tribe Marmotini was larger in scatterhoarders, but not in other tribes. Scatterhoarding in tribe Marmotini was more likely in species with lower population densities while scatterhoarding in tribe Sciurini was associated with warmer climates. Red squirrel larderhoarding intensity was positively related to population density but not climate, implicating food competition or pilferage as an important mechanism mediating caching behaviour. Our results are consistent with previous smaller-scale studies on food caching and indicate the evolutionary patterns of mammalian food caching are broadly generalizable. Given the lability of caching behaviour as evidenced by the variability of our results at finer phylogenetic scales, comparative analyses must consider taxonomic scale. Applying our results to conservation could prove useful as changes in population density or climate may select for different food caching strategies and thus can inform management of threatened and endangered species and their habitats.

Image-based recognition of parasitoid wasps using advanced neural networks.

Hymenoptera has some of the highest diversity and number of individuals among insects. Many of these species potentially play key roles as food sources, pest controllers and pollinators. However, little is known about the diversity and biology and ~80% of the species have not yet been described. Classical taxonomy based on morphology is a rather slow process but DNA barcoding has already brought considerable progress in identification. Innovative methods such as image-based identification and automation can further speed up the process. We present a proof of concept for image data recognition of a parasitic wasp family, the Diapriidae (Hymenoptera), obtained as part of the GBOL III project. These tiny (1.2-4.5mm) wasps were photographed and identified using DNA barcoding to provide a solid ground truth for training a neural network. Taxonomic identification was used down to the genus level. Subsequently, three different neural network architectures were trained, evaluated and optimised. As a result, 11 different genera of diaprids and one mixed group of 'other Hymenoptera' can be classified with an average accuracy of 96%. Additionally, the sex of the specimen can be classified automatically with an accuracy of >97%.

Protocol to discover machine-readable entities of the ecosystem management actions taxonomy.

The ecosystem management actions taxonomy (EMAT) consists of actions taken by humans and wildlife that affect an ecosystem. Here, I present a protocol for discovering machine-readable entities of the EMAT. I describe steps for acquiring stories from online locations, collecting them into a story file, and processing them through a software package to extract those actions that match EMAT taxa. I then detail procedures for using the story file to learn new EMAT taxa.

SeqCode in the golden age of prokaryotic systematics.

The SeqCode is a new code of prokaryotic nomenclature that was developed to validate taxon names using genome sequences as the type material. The present article provides an independent view about the SeqCode, highlighting its history, current status, basic features, pros and cons, and use to date. We also discuss important topics to consider for validation of novel prokaryotic taxon names using genomes as the type material. Owing to significant advances in metagenomics and cultivation methods, hundreds of novel prokaryotic species are expected to be discovered in the coming years. This manuscript aims to stimulate and enrich the debate around the use of the SeqCode in the upcoming golden age of prokaryotic taxon discovery and systematics.

Knowledge-guided generative artificial intelligence for automated taxonomy learning from drug labels.

OBJECTIVES: To automatically construct a drug indication taxonomy from drug labels using generative Artificial Intelligence (AI) represented by the Large Language Model (LLM) GPT-4 and real-world evidence (RWE). MATERIALS AND METHODS: We extracted indication terms from 46 421 free-text drug labels using GPT-4, iteratively and recursively generated indication concepts and inferred indication concept-to-concept and concept-to-term subsumption relations by integrating GPT-4 with RWE, and created a drug indication taxonomy. Quantitative and qualitative evaluations involving domain experts were performed for cardiovascular (CVD), Endocrine, and Genitourinary system diseases. RESULTS: 2909 drug indication terms were extracted and assigned into 24 high-level indication categories (ie, initially generated concepts), each of which was expanded into a sub-taxonomy. For example, the CVD sub-taxonomy contains 242 concepts, spanning a depth of 11, with 170 being leaf nodes. It collectively covers a total of 234 indication terms associated with 189 distinct drugs. The accuracies of GPT-4 on determining the drug indication hierarchy exceeded 0.7 with "good to very good" inter-rater reliability. However, the accuracies of the concept-to-term subsumption relation checking varied greatly, with "fair to moderate" reliability. DISCUSSION AND CONCLUSION: We successfully used generative AI and RWE to create a taxonomy, with drug indications adequately consistent with domain expert expectations. We show that LLMs are good at deriving their own concept hierarchies but still fall short in determining the subsumption relations between concepts and terms in unregulated language from free-text drug labels, which is the same hard task for human experts.

A taxonomy for advancing systematic error analysis in multi-site electronic health record-based clinical concept extraction.

BACKGROUND: Error analysis plays a crucial role in clinical concept extraction, a fundamental subtask within clinical natural language processing (NLP). The process typically involves a manual review of error types, such as contextual and linguistic factors contributing to their occurrence, and the identification of underlying causes to refine the NLP model and improve its performance. Conducting error analysis can be complex, requiring a combination of NLP expertise and domain-specific knowledge. Due to the high heterogeneity of electronic health record (EHR) settings across different institutions, challenges may arise when attempting to standardize and reproduce the error analysis process. OBJECTIVES: This study aims to facilitate a collaborative effort to establish common definitions and taxonomies for capturing diverse error types, fostering community consensus on error analysis for clinical concept extraction tasks. MATERIALS AND METHODS: We iteratively developed and evaluated an error taxonomy based on existing literature, standards, real-world data, multisite case evaluations, and community feedback. The finalized taxonomy was released in both .dtd and .owl formats at the Open Health Natural Language Processing Consortium. The taxonomy is compatible with several different open-source annotation tools, including MAE, Brat, and MedTator. RESULTS: The resulting error taxonomy comprises 43 distinct error classes, organized into 6 error dimensions and 4 properties, including model type (symbolic and statistical machine learning), evaluation subject (model and human), evaluation level (patient, document, sentence, and concept), and annotation examples. Internal and external evaluations revealed strong variations in error types across methodological approaches, tasks, and EHR settings. Key points emerged from community feedback, including the need to enhancing clarity, generalizability, and usability of the taxonomy, along with dissemination strategies. CONCLUSION: The proposed taxonomy can facilitate the acceleration and standardization of the error analysis process in multi-site settings, thus improving the provenance, interpretability, and portability of NLP models. Future researchers could explore the potential direction of developing automated or semi-automated methods to assist in the classification and standardization of error analysis.

Random-Effects Substitution Models for Phylogenetics via Scalable Gradient Approximations.

Phylogenetic and discrete-trait evolutionary inference depend heavily on an appropriate characterization of the underlying character substitution process. In this paper, we present random-effects substitution models that extend common continuous-time Markov chain models into a richer class of processes capable of capturing a wider variety of substitution dynamics. As these random-effects substitution models often require many more parameters than their usual counterparts, inference can be both statistically and computationally challenging. Thus, we also propose an efficient approach to compute an approximation to the gradient of the data likelihood with respect to all unknown substitution model parameters. We demonstrate that this approximate gradient enables scaling of sampling-based inference, namely Bayesian inference via Hamiltonian Monte Carlo, under random-effects substitution models across large trees and state-spaces. Applied to a dataset of 583 SARS-CoV-2 sequences, an HKY model with random-effects shows strong signals of nonreversibility in the substitution process, and posterior predictive model checks clearly show that it is a more adequate model than a reversible model. When analyzing the pattern of phylogeographic spread of 1441 influenza A virus (H3N2) sequences between 14 regions, a random-effects phylogeographic substitution model infers that air travel volume adequately predicts almost all dispersal rates. A random-effects state-dependent substitution model reveals no evidence for an effect of arboreality on the swimming mode in the tree frog subfamily Hylinae. Simulations reveal that random-effects substitution models can accommodate both negligible and radical departures from the underlying base substitution model. We show that our gradient-based inference approach is over an order of magnitude more time efficient than conventional approaches.

Inferring the Evolutionary Model of Community-Structuring Traits with Convolutional Kitchen Sinks.

When communities are assembled through processes such as filtering or limiting similarity acting on phylogenetically conserved traits, the evolutionary signature of those traits may be reflected in patterns of community membership. We show how the model of trait evolution underlying community-structuring traits can be inferred from community membership data using both a variation of a traditional eco-phylogenetic metric-the mean pairwise phylogenetic distance (MPD) between taxa-and a recent machine learning tool, Convolutional Kitchen Sinks (CKS). Both methods perform well across a range of phylogenetically informative evolutionary models, but CKS outperforms MPD as tree size increases. We demonstrate CKS by inferring the evolutionary history of freeze tolerance in angiosperms. Our analysis is consistent with a late burst model, suggesting freeze tolerance evolved recently. We suggest that multiple data types that are ordered on phylogenies, such as trait values, species interactions, or community presence/absence, are good candidates for CKS modeling because the generative models produce structured differences between neighboring points that CKS is well-suited for. We introduce the R package kitchen to perform CKS for generic application of the technique.

Nomenclatural stability and the longevity of helminth species names.

Although most Latin binomial names of species are valid, many are eventually unaccepted when they are found to be synonyms of previously described species, or superseded by a new combination when the species they denote are moved to a different genus. What proportion of parasite species names become unaccepted over time, and how long does it take for incorrect names to become unaccepted? Here, we address these questions using a dataset comprising thousands of species names of parasitic helminths from four higher taxa (Acanthocephala, Nematoda, Cestoda, and Trematoda). Overall, among species names proposed in the past two-and-a-half centuries, nearly one-third have since been unaccepted, the most common reason being that they have been superseded by a new combination. A greater proportion of older names (proposed pre-1950) have since been unaccepted compared to names proposed more recently, however most taxonomic acts leading to species names being unaccepted (through either synonymy or reclassification) occurred in the past few decades. Overall, the average longevity of helminth species names that are currently unaccepted was 29 years; although many remained in use for over 100 years, about 50% of the total were invalidated within 20 years of first being proposed. The patterns observed were roughly the same for all four higher helminth taxa considered here. Our results provide a quantitative illustration of the self-correcting nature of parasite taxonomy, and can also help to calibrate future estimates of total parasite biodiversity.

Application and Comparison of Machine Learning and Database-Based Methods in Taxonomic Classification of High-Throughput Sequencing Data.

The advent of high-throughput sequencing technologies has not only revolutionized the field of bioinformatics but has also heightened the demand for efficient taxonomic classification. Despite technological advancements, efficiently processing and analyzing the deluge of sequencing data for precise taxonomic classification remains a formidable challenge. Existing classification approaches primarily fall into two categories, database-based methods and machine learning methods, each presenting its own set of challenges and advantages. On this basis, the aim of our study was to conduct a comparative analysis between these two methods while also investigating the merits of integrating multiple database-based methods. Through an in-depth comparative study, we evaluated the performance of both methodological categories in taxonomic classification by utilizing simulated data sets. Our analysis revealed that database-based methods excel in classification accuracy when backed by a rich and comprehensive reference database. Conversely, while machine learning methods show superior performance in scenarios where reference sequences are sparse or lacking, they generally show inferior performance compared with database methods under most conditions. Moreover, our study confirms that integrating multiple database-based methods does, in fact, enhance classification accuracy. These findings shed new light on the taxonomic classification of high-throughput sequencing data and bear substantial implications for the future development of computational biology. For those interested in further exploring our methods, the source code of this study is publicly available on https://github.com/LoadStar822/Genome-Classifier-Performance-Evaluator. Additionally, a dedicated webpage showcasing our collected database, data sets, and various classification software can be found at http://lab.malab.cn/~tqz/project/taxonomic/.

Taxonomic discordance of immersive realities in dentistry: A systematic scoping review.

OBJECTIVES: This review aimed to map taxonomy frameworks, descriptions, and applications of immersive technologies in the dental literature. DATA: The Preferred reporting items for systematic reviews and meta-analyses extension for scoping reviews (PRISMA-ScR) guidelines was followed, and the protocol was registered at open science framework platform (https://doi.org/10.17605/OSF.IO/H6N8M). SOURCES: Systematic search was conducted in MEDLINE (via PubMed), Scopus, and Cochrane Library databases, and complemented by manual search. STUDY SELECTION: A total of 84 articles were included, with 81 % between 2019 and 2023. Most studies were experimental (62 %), including education (25 %), protocol feasibility (20 %), in vitro (11 %), and cadaver (6 %). Other study types included clinical report/technique article (24 %), clinical study (9 %), technical note/tip to reader (4 %), and randomized controlled trial (1 %). Three-quarters of the included studies were published in oral and maxillofacial surgery (38 %), dental education (26 %), and implant (12 %) disciplines. Methods of display included head mounted display device (HMD) (55 %), see through screen (32 %), 2D screen display (11 %), and projector display (2 %). Descriptions of immersive realities were fragmented and inconsistent with lack of clear taxonomy framework for the umbrella and the subset terms including virtual reality (VR), augmented reality (AR), mixed reality (MR), augmented virtuality (AV), extended reality, and X reality. CONCLUSIONS: Immersive reality applications in dentistry are gaining popularity with a notable surge in the number of publications in the last 5 years. Ambiguities are apparent in the descriptions of immersive realities. A taxonomy framework based on method of display (full or partial) and reality class (VR, AR, or MR) is proposed. CLINICAL SIGNIFICANCE: Understanding different reality classes can be perplexing due to their blurred boundaries and conceptual overlapping. Immersive technologies offer novel educational and clinical applications. This domain is fast developing. With the current fragmented and inconsistent terminologies, a comprehensive taxonomy framework is necessary.